Move the optimized XOR into lib/raid and include it it in the main
xor.ko instead of building a separate module for it.

Signed-off-by: Christoph Hellwig <[email protected]>
---
 arch/arm64/include/asm/xor.h                  | 58 +------------------
 arch/arm64/lib/Makefile                       |  6 --
 lib/raid/xor/Makefile                         |  5 ++
 lib/raid/xor/arm64/xor-neon-glue.c            | 57 ++++++++++++++++++
 .../lib => lib/raid/xor/arm64}/xor-neon.c     | 21 ++-----
 5 files changed, 69 insertions(+), 78 deletions(-)
 create mode 100644 lib/raid/xor/arm64/xor-neon-glue.c
 rename {arch/arm64/lib => lib/raid/xor/arm64}/xor-neon.c (95%)

diff --git a/arch/arm64/include/asm/xor.h b/arch/arm64/include/asm/xor.h
index bfa6122f55ce..81718f010761 100644
--- a/arch/arm64/include/asm/xor.h
+++ b/arch/arm64/include/asm/xor.h
@@ -1,73 +1,21 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * arch/arm64/include/asm/xor.h
- *
  * Authors: Jackie Liu <[email protected]>
  * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
  */
 
-#include <linux/hardirq.h>
 #include <asm-generic/xor.h>
-#include <asm/hwcap.h>
 #include <asm/simd.h>
 
-#ifdef CONFIG_KERNEL_MODE_NEON
-
-extern struct xor_block_template const xor_block_inner_neon;
-
-static void
-xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
-          const unsigned long * __restrict p2)
-{
-       scoped_ksimd()
-               xor_block_inner_neon.do_2(bytes, p1, p2);
-}
-
-static void
-xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
-          const unsigned long * __restrict p2,
-          const unsigned long * __restrict p3)
-{
-       scoped_ksimd()
-               xor_block_inner_neon.do_3(bytes, p1, p2, p3);
-}
-
-static void
-xor_neon_4(unsigned long bytes, unsigned long * __restrict p1,
-          const unsigned long * __restrict p2,
-          const unsigned long * __restrict p3,
-          const unsigned long * __restrict p4)
-{
-       scoped_ksimd()
-               xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4);
-}
-
-static void
-xor_neon_5(unsigned long bytes, unsigned long * __restrict p1,
-          const unsigned long * __restrict p2,
-          const unsigned long * __restrict p3,
-          const unsigned long * __restrict p4,
-          const unsigned long * __restrict p5)
-{
-       scoped_ksimd()
-               xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5);
-}
-
-static struct xor_block_template xor_block_arm64 = {
-       .name   = "arm64_neon",
-       .do_2   = xor_neon_2,
-       .do_3   = xor_neon_3,
-       .do_4   = xor_neon_4,
-       .do_5   = xor_neon_5
-};
+extern struct xor_block_template xor_block_arm64;
+void __init xor_neon_init(void);
 
 #define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
+       xor_neon_init();
        xor_register(&xor_block_8regs);
        xor_register(&xor_block_32regs);
        if (cpu_has_neon())
                xor_register(&xor_block_arm64);
 }
-
-#endif /* ! CONFIG_KERNEL_MODE_NEON */
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 633e5223d944..448c917494f3 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -5,12 +5,6 @@ lib-y          := clear_user.o delay.o copy_from_user.o        
        \
                   memset.o memcmp.o strcmp.o strncmp.o strlen.o        \
                   strnlen.o strchr.o strrchr.o tishift.o
 
-ifeq ($(CONFIG_KERNEL_MODE_NEON), y)
-obj-$(CONFIG_XOR_BLOCKS)       += xor-neon.o
-CFLAGS_xor-neon.o              += $(CC_FLAGS_FPU)
-CFLAGS_REMOVE_xor-neon.o       += $(CC_FLAGS_NO_FPU)
-endif
-
 lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
diff --git a/lib/raid/xor/Makefile b/lib/raid/xor/Makefile
index fb760edae54b..3c13851219e5 100644
--- a/lib/raid/xor/Makefile
+++ b/lib/raid/xor/Makefile
@@ -12,8 +12,13 @@ xor-$(CONFIG_ALPHA)          += alpha/xor.o
 xor-$(CONFIG_ARM)              += arm/xor.o
 ifeq ($(CONFIG_ARM),y)
 xor-$(CONFIG_KERNEL_MODE_NEON) += arm/xor-neon.o arm/xor-neon-glue.o
+else
+xor-$(CONFIG_KERNEL_MODE_NEON) += arm64/xor-neon.o arm64/xor-neon-glue.o
 endif
 
 
 CFLAGS_arm/xor-neon.o          += $(CC_FLAGS_FPU)
 CFLAGS_REMOVE_arm/xor-neon.o   += $(CC_FLAGS_NO_FPU)
+
+CFLAGS_arm64/xor-neon.o                += $(CC_FLAGS_FPU)
+CFLAGS_REMOVE_arm64/xor-neon.o += $(CC_FLAGS_NO_FPU)
diff --git a/lib/raid/xor/arm64/xor-neon-glue.c 
b/lib/raid/xor/arm64/xor-neon-glue.c
new file mode 100644
index 000000000000..067a2095659a
--- /dev/null
+++ b/lib/raid/xor/arm64/xor-neon-glue.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Authors: Jackie Liu <[email protected]>
+ * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
+ */
+
+#include <linux/raid/xor_impl.h>
+#include <asm/simd.h>
+#include <asm/xor.h>
+
+extern struct xor_block_template const xor_block_inner_neon;
+
+static void
+xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
+          const unsigned long * __restrict p2)
+{
+       scoped_ksimd()
+               xor_block_inner_neon.do_2(bytes, p1, p2);
+}
+
+static void
+xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
+          const unsigned long * __restrict p2,
+          const unsigned long * __restrict p3)
+{
+       scoped_ksimd()
+               xor_block_inner_neon.do_3(bytes, p1, p2, p3);
+}
+
+static void
+xor_neon_4(unsigned long bytes, unsigned long * __restrict p1,
+          const unsigned long * __restrict p2,
+          const unsigned long * __restrict p3,
+          const unsigned long * __restrict p4)
+{
+       scoped_ksimd()
+               xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4);
+}
+
+static void
+xor_neon_5(unsigned long bytes, unsigned long * __restrict p1,
+          const unsigned long * __restrict p2,
+          const unsigned long * __restrict p3,
+          const unsigned long * __restrict p4,
+          const unsigned long * __restrict p5)
+{
+       scoped_ksimd()
+               xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5);
+}
+
+struct xor_block_template xor_block_arm64 = {
+       .name   = "arm64_neon",
+       .do_2   = xor_neon_2,
+       .do_3   = xor_neon_3,
+       .do_4   = xor_neon_4,
+       .do_5   = xor_neon_5
+};
diff --git a/arch/arm64/lib/xor-neon.c b/lib/raid/xor/arm64/xor-neon.c
similarity index 95%
rename from arch/arm64/lib/xor-neon.c
rename to lib/raid/xor/arm64/xor-neon.c
index 8fffebfa17b2..8d2d185090db 100644
--- a/arch/arm64/lib/xor-neon.c
+++ b/lib/raid/xor/arm64/xor-neon.c
@@ -1,14 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * arch/arm64/lib/xor-neon.c
- *
  * Authors: Jackie Liu <[email protected]>
  * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
  */
 
-#include <linux/raid/xor.h>
-#include <linux/module.h>
+#include <linux/raid/xor_impl.h>
+#include <linux/cache.h>
 #include <asm/neon-intrinsics.h>
+#include <asm/xor.h>
 
 static void xor_arm64_neon_2(unsigned long bytes, unsigned long * __restrict 
p1,
        const unsigned long * __restrict p2)
@@ -179,7 +178,6 @@ struct xor_block_template xor_block_inner_neon 
__ro_after_init = {
        .do_4   = xor_arm64_neon_4,
        .do_5   = xor_arm64_neon_5,
 };
-EXPORT_SYMBOL(xor_block_inner_neon);
 
 static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
 {
@@ -317,22 +315,11 @@ static void xor_arm64_eor3_5(unsigned long bytes,
        } while (--lines > 0);
 }
 
-static int __init xor_neon_init(void)
+void __init xor_neon_init(void)
 {
        if (cpu_have_named_feature(SHA3)) {
                xor_block_inner_neon.do_3 = xor_arm64_eor3_3;
                xor_block_inner_neon.do_4 = xor_arm64_eor3_4;
                xor_block_inner_neon.do_5 = xor_arm64_eor3_5;
        }
-       return 0;
 }
-module_init(xor_neon_init);
-
-static void __exit xor_neon_exit(void)
-{
-}
-module_exit(xor_neon_exit);
-
-MODULE_AUTHOR("Jackie Liu <[email protected]>");
-MODULE_DESCRIPTION("ARMv8 XOR Extensions");
-MODULE_LICENSE("GPL");
-- 
2.47.3


Reply via email to